{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/agent-based-model-calibration-using-machine","title":"Agent-Based Model Calibration using Machine Learning Surrogates","arxiv_id":"1703.10639","date":"2017-03-30","proceeding":null,"authors":["Francesco Lamperti","Andrea Roventini","Amir Sani"],"abstract":"Taking agent-based models (ABM) closer to the data is an open challenge. This\npaper explicitly tackles parameter space exploration and calibration of ABMs\ncombining supervised machine-learning and intelligent sampling to build a\nsurrogate meta-model. The proposed approach provides a fast and accurate\napproximation of model behaviour, dramatically reducing computation time. In\nthat, our machine-learning surrogate facilitates large scale explorations of\nthe parameter-space, while providing a powerful filter to gain insights into\nthe complex functioning of agent-based models. The algorithm introduced in this\npaper merges model simulation and output analysis into a surrogate meta-model,\nwhich substantially ease ABM calibration. We successfully apply our approach to\nthe Brock and Hommes (1998) asset pricing model and to the \"Island\" endogenous\ngrowth model (Fagiolo and Dosi, 2003). Performance is evaluated against a\nrelatively large out-of-sample set of parameter combinations, while employing\ndifferent user-defined statistical tests for output analysis. The results\ndemonstrate the capacity of machine learning surrogates to facilitate fast and\nprecise exploration of agent-based models' behaviour over their often rugged\nparameter spaces.","url_abs":"http://arxiv.org/abs/1703.10639v2","url_pdf":"http://arxiv.org/pdf/1703.10639v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"agent-based-model-calibration-using-machine","repo_url":"https://github.com/ivisonadam/ABM_callibration","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"model","task_name":"model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.10639","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}